Reto-01

Inicio al modelaje de datos

OBJETIVO

• Crear una regresion lineal

REQUISITOS

1. Contar con R studio.
2. Usar la carpeta de trabajo Sesion08/Reto-01

DESARROLLO

Usaremos la base de mtcars y crearemos un scatter.smooth para ver la relacion entre peso (variable wt) y millas por galon (variable mpg). Despues checaremos la correlacion entre ambas variables y finalmente crearemos un modelo lineal, lo visualizaremos y sacaremos su resumen.

Usaremos la base de “cars” ya disponible en R. Mediante un scatterplot podremos ver la relacion entre distancia y velocidad. La funcion para crearlo es scatter.smooth(x,y) y podemos anadirle un titulo al grafico con la funcion, main=""

library(corrplot)

corrplot 0.84 loaded

Luego buscaremos la correlacion entre ambas variables:

cor(mtcars$wt, mtcars$mpg)

[1] -0.8676594

modlin <- lm(wt ~ mpg, data=mtcars)  
print(modlin)

Call:
lm(formula = wt ~ mpg, data = mtcars)

Coefficients:
(Intercept)          mpg  
     6.0473      -0.1409  

summary(modlin)

Call:
lm(formula = wt ~ mpg, data = mtcars)

Residuals:
    Min      1Q  Median      3Q     Max 
-0.6516 -0.3490 -0.1381  0.3190  1.3684 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  6.04726    0.30869  19.590  < 2e-16 ***
mpg         -0.14086    0.01474  -9.559 1.29e-10 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.4945 on 30 degrees of freedom
Multiple R-squared:  0.7528,    Adjusted R-squared:  0.7446 
F-statistic: 91.38 on 1 and 30 DF,  p-value: 1.294e-10

data(mtcars)
M <- cor(mtcars)

##  different color series
col1 <- colorRampPalette(c("#7F0000", "red", "#FF7F00", "yellow", "white",
                           "cyan", "#007FFF", "blue","#00007F"))
col2 <- colorRampPalette(c("#67001F", "#B2182B", "#D6604D", "#F4A582",
                           "#FDDBC7", "#FFFFFF", "#D1E5F0", "#92C5DE",
                           "#4393C3", "#2166AC", "#053061"))
col3 <- colorRampPalette(c("red", "white", "blue"))
col4 <- colorRampPalette(c("#7F0000", "red", "#FF7F00", "yellow", "#7FFF7F",
                           "cyan", "#007FFF", "blue", "#00007F"))
wb <- c("white", "black")

par(ask = TRUE)

corrplot(M, method = "number", col = "black", cl.pos = "n")

corrplot(M, method = "number")

corrplot(M)

corrplot(M, order = "AOE")

corrplot(M, order = "AOE", addCoef.col = "grey")

corrplot(M, order = "AOE", col = col1(20), cl.length = 21, addCoef.col = "grey")

corrplot(M, order = "AOE", col = col1(10), addCoef.col = "grey")

corrplot(M, order = "AOE", col = col2(200))

corrplot(M, order = "AOE", col = col2(200), addCoef.col = "grey")

corrplot(M, order = "AOE", col = col2(20), cl.length = 21, addCoef.col = "grey")

corrplot(M, order = "AOE", col = col2(10), addCoef.col = "grey")

corrplot(M, order = "AOE", col = col3(100))

corrplot(M, order = "AOE", col = col3(10))

corrplot(M, method = "color", col = col1(20), cl.length = 21, order = "AOE",
         addCoef.col = "grey")

corrplot(M, method = "square", col = col2(200), order = "AOE")

corrplot(M, method = "ellipse", col = col1(200), order = "AOE")

corrplot(M, method = "shade", col = col3(20), order = "AOE")

corrplot(M, method = "pie", order = "AOE")

## col = wb
corrplot(M, col = wb, order = "AOE", outline = TRUE, cl.pos = "n")

## like Chinese wiqi, suit for either on screen or white-black print.
corrplot(M, col = wb, bg = "gold2",  order = "AOE", cl.pos = "n")

## mixed methods: It's more efficient if using function "corrplot.mixed"
## circle + ellipse
corrplot(M, order = "AOE", type = "upper", tl.pos = "d")
corrplot(M, add = TRUE, type = "lower", method = "ellipse", order = "AOE",
         diag = FALSE, tl.pos = "n", cl.pos = "n")

## circle + square
corrplot(M, order = "AOE",type = "upper", tl.pos = "d")
corrplot(M, add = TRUE, type = "lower", method = "square", order = "AOE",
         diag = FALSE, tl.pos = "n", cl.pos = "n")

## circle + colorful number
corrplot(M, order = "AOE", type = "upper", tl.pos = "d")
corrplot(M, add = TRUE, type = "lower", method = "number", order = "AOE",
         diag = FALSE, tl.pos = "n", cl.pos = "n")

## circle + black number
corrplot(M, order = "AOE", type = "upper", tl.pos = "tp")
corrplot(M, add = TRUE, type = "lower", method = "number", order = "AOE",
         col = "black", diag = FALSE, tl.pos = "n", cl.pos = "n")

## order is hclust and draw rectangles
corrplot(M, order = "hclust")

corrplot(M, order = "hclust", addrect = 2)

corrplot(M, order = "hclust", addrect = 3, rect.col = "red")

corrplot(M, order = "hclust", addrect = 4, rect.col = "blue")

corrplot(M, order = "hclust", hclust.method = "ward.D2", addrect = 4)

## visualize a  matrix in [0, 1]
corrplot(abs(M), order = "AOE", cl.lim = c(0,1))

corrplot(abs(M), order = "AOE", col = col1(20), cl.lim = c(0,1))

corrplot(abs(M), order = "AOE", col = col3(200), cl.lim = c(0,1))

## visualize a  matrix in [-100, 100]
ran <- round(matrix(runif(225, -100,100), 15))
corrplot(ran, is.corr = FALSE)

corrplot(ran, is.corr = FALSE, cl.lim = c(-100, 100))

## text-labels and plot type
corrplot(M, order = "AOE", tl.srt = 45)

corrplot(M, order = "AOE", tl.srt = 60)

corrplot(M, order = "AOE", tl.pos = "d", cl.pos = "n")

corrplot(M, order = "AOE", diag = FALSE, tl.pos = "d")

corrplot(M, order = "AOE", type = "upper")

corrplot(M, order = "AOE", type = "upper", diag = FALSE)

corrplot(M, order = "AOE", type = "lower", cl.pos = "b")

corrplot(M, order = "AOE", type = "lower", cl.pos = "b", diag = FALSE)

## an animation of changing confidence interval in different significance level
## begin.animaton
par(ask = FALSE)
for (i in seq(0.1, 0, -0.005)) {
  tmp <- cor.mtest(mtcars, conf.level = 1 - i)
  corrplot(M, p.mat = tmp$p, low = tmp$lowCI, upp = tmp$uppCI, order = "hclust",
           pch.col = "red", sig.level = i, plotCI = "rect", cl.pos = "n",
           mar = c(0, 0, 1, 0),
           title = substitute(alpha == x,
                              list(x = format(i, digits = 3, nsmall = 3))))
  Sys.sleep(0.15)
}

## end.animaton